Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    incident reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ในช
    -0.07
    τιν
    -0.06
    circ
    -0.06
    сам
    -0.06
     studying
    -0.06
    RR
    -0.06
    œ
    -0.06
    ecal
    -0.06
    MK
    -0.06
     autonom
    -0.06
    POSITIVE LOGITS
     κατά
    0.07
    robat
    0.06
     Kaepernick
    0.06
    .forChild
    0.06
    .Appearance
    0.06
     Orion
    0.06
     serialize
    0.06
     ImmutableList
    0.06
     clans
    0.06
     widget
    0.06
    Act Density 0.079%

    No Known Activations